Skip to main content
POST

Overview

Reads a text aloud with any voice from List Voices: a library voice or one of your own. It is the text-to-speech voiceover of the dashboard editor, with the same model, settings and price. Use it to preview a voice on your own script, or to get a voiceover file for your own editing.
  • Up to 1,200 characters per call, the editor’s limit.
  • audio tunes the voice: speed (0.7 to 1.2, default 1.0), stability (0 to 1, default 0.5) and similarityBoost (0 to 1, default 0.75). These are the same settings the create endpoints take as audio.
  • The answer comes when the audio is ready, usually in a few seconds.
The MP3 is saved to your team’s voiceovers (the editor’s generated voiceovers, counted against your storage) and url links to it for 10 minutes: download it right away. There is no endpoint to fetch it again later.
Price: 5 credits per started 1,000 characters (1 to 1,000 characters: 5 credits; 1,001 to 1,200: 10). They are charged before generating and given back if it fails. BYOK teams speak with their own ElevenLabs key and are not charged.

Errors

Send an Idempotency-Key header to retry safely after a timeout: the same key answers with the first voiceover instead of generating (and charging) it again.

Authorizations

x-api-key
string
header
required

Headers

Idempotency-Key
string

Makes the request safe to retry. 1-255 printable ASCII characters, one per operation (your job id, or a UUID you store), reused on every retry. Within 24 hours the same key with the same body answers with the first response and the header Idempotent-Replayed: true, without running or charging again. Keys are scoped to your team and the endpoint. 5xx answers and refusals before anything ran (401, 402, 403, 409, 429) are not kept. See Idempotency.

Required string length: 1 - 255
Pattern: ^[\x20-\x7E]+$

Body

application/json
voiceId
string
required

A voice from List Voices: its id (a library voice, or one of your team's own voices). Another team's voice, an unknown id, or one of your clones that is unavailable in your current key mode answers 400.

Maximum string length: 100
text
string
required

What the voice says. Up to 1,200 characters (trimmed).

Required string length: 1 - 1200
audio
object

Voice settings, as in the editor. Each one is optional; a missing one takes its default. An unknown key answers 400.

name
string

Name of the voiceover in the editor. A generated file name when omitted.

Maximum string length: 100

Response

Speech generated

success
boolean
message
string
data
object